shootout-mandelbrot: Either 10-20% or 80-100% improvement. #14203
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
More improvements to our shootout benchmarks are welcome. |
|
Sweet, this is awesome! |
|
During the rollup, an assertion failed during the mandelbrot benchmark, I didn't check to make sure that this was the cause of the commit, but I suspect that it may be. |
|
@alexcrichton Forgot to account for N=1000 when upping the worker count. Fixed. |
lnicola
pushed a commit
to lnicola/rust
that referenced
this pull request
Mar 13, 2023
…=lnicola fix: Add check for extra path segments after a fully qualified one `type A = <()>;` is parsed just fine by rust-analyzer, but then rejected by rustc: ``` error: expected `::`, found `;` --> x.rs:7:14 | 7 | type A = <()>; | ^ expected `::` ``` Fixed by adding a lookahead for the `::` token after fully-qualified path segments.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Not sure if we're accepting SIMD usage in the main tree, so the first commit is just unrolling the loop a bit to calculate two bits at a time, this gives a 2second speedup from 12s => 10s on my i5.
The second commit using SIMD which brings it down to about 6s. It also precomputes initial values (which doesn't help much, but it is noticeable).
If we're allowing SIMD in the benchmarks, I can squash to the 2nd commit, otherwise I can kill the 2nd commit and leave the first.